Skip to content

[Bug]: NVIDIAEmbedding(model="NV-Embed-QA") returns 404 when calling any method #19140

Open
@jakegill

Description

@jakegill

Bug Description

See: llama_index / embeddings / nvidia / utils.py

    "NV-Embed-QA": Model(
        id="NV-Embed-QA",
        model_type="embedding",
        endpoint="https://ai.api.nvidia.com/v1/retrieval/nvidia", #(DOES NOT EXIST)
        aliases=[
            "ai-embed-qa-4",
            "playground_nvolveqa_40k",
            "nvolveqa_40k",
        ],
    ),

Version

Most recent

Steps to Reproduce

from llama_index.embeddings.nvidia import NVIDIAEmbedding
import os
os.environ["NVIDIA_API_KEY"] = "YOUR NVIDIA KEY"

embed_model = NVIDIAEmbedding(model="NV-Embed-QA")
vec = embed_model.get_text_embedding("test")

Relevant Logs/Tracbacks

File "C:\Python312\Lib\site-packages\llama_index_instrumentation\dispatcher.py", line 319, in wrapper
    result = func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\llama_index\core\base\embeddings\base.py", line 148, in get_query_embedding
    query_embedding = self._get_query_embedding(query)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\llama_index_instrumentation\dispatcher.py", line 319, in wrapper
    result = func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\llama_index\embeddings\nvidia\base.py", line 218, in _get_query_embedding
    self._client.embeddings.create(
  File "C:\Python312\Lib\site-packages\openai\resources\embeddings.py", line 129, in create
    return self._post(
           ^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\openai\_base_client.py", line 1249, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Python312\Lib\site-packages\openai\_base_client.py", line 1037, in request
    raise self._make_status_error_from_response(err.response) from None
openai.NotFoundError: 404 page not found

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't workingtriageIssue needs to be triaged/prioritized

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions